01
Action and sports
Multi-person movement — pair skating, a sword duel, a dance routine — that stays physically plausible through the whole take.
AI Video Model
Seedance 2.0
Multimodal video direction with native synchronized sound
Combine text, images, video, and audio to direct coherent motion, camera work, performance, and sound in one generation brief.
Creative workspace
Seedance 2.0
52
What is Seedance 2.0?
Seedance 2.0 is ByteDance Seed's video model built on a unified audio-video architecture: it takes text, images, video, and audio together and returns a multi-shot clip of up to 15 seconds with two-channel sound generated alongside the picture.
How the people who built the model describe it:
“Built with a unified multimodal audio-video joint generation architecture, Seedance 2.0 supports four input modalities: text, image, audio, and video.”
Seedance 2.0 at a glance
- Inputs
- Text + multimodal refs
- Duration
- 4–15 seconds
- Audio
- Native synchronized
What you can make with the Seedance 2.0 tool
These are the jobs people actually bring to Seedance 2.0, and the settings each one needs.
02
Storyboard to shot
Hand it a script page or storyboard as an image and let it follow the shot sizes, camera moves, and copy you drew.
03
Ads and explainers
ByteDance positions it for commercial advertising and explainer videos, where product, motion, and sound all have to land in one take.
Seedance 2.0
A workspace shaped for the model
Seedance 2.0 puts the handful of controls that change the result most in front of you, and keeps the rest out of the way.
Official model example · ByteDance Seed
01
Complex motion that obeys physics
ByteDance’s headline improvement over 1.5 is motion stability: multi-subject interaction and fast action — the lifts and spins of pair skating — hold together instead of melting.
Official model example · ByteDance Seed
02
All-round multimodal reference
Mix up to nine images, three video clips, and three audio clips with your prompt; the model can take composition, motion, camera movement, effects, or sound from any of them.
Official model example · ByteDance Seed
03
Instructions followed precisely
Instruction following and consistency were rebuilt, so detailed direction — who does what, in which order, framed how — shows up as written. Extending and editing a clip are supported too.
Official model example · ByteDance Seed
04
Two-channel, synchronized sound
Audio is generated with the picture in stereo: blades, footsteps, fabric, and ambience land on the right frame and on the right side of the mix.
Official model example · ByteDance Seed
05
Built for real production work
Up to 15 seconds of multi-shot audio-video in one generation, adaptable to advertising, explainers, and short drama rather than a single showcase shot.
Seedance 2.0
Choose with context
Where Seedance 2.0 is the right call, and where a different model does the job better.
Compared with Seedance 2 Mini
Broader resolution range and premium production settings
Compared with H3
Flexible resolution ladder versus H3’s fixed 2K focus
Best decision signal
You need multimodal control and synchronized audio
From brief to studio in three steps
01
Set the creative anchor
Write the idea and add any source or reference material the tool needs.
02
Shape the output
Choose the model, format, resolution, and duration that match delivery.
03
Continue in Studio
Review the complete draft in the shared conversation flow. Generation will be enabled when the model API is connected.
Seedance 2.0 FAQ
Compare the Seedance 2 models
Compare output length, resolution, references, aspect ratios, and audio support before choosing a model for your next video.
| Capability | Seedance 2.0Current model | Seedance 2 Mini | Seedance 2.5 |
|---|---|---|---|
| Best for | High-resolution production | Lightweight, economical drafts | Longer, coherent storytelling |
| Output duration | 4–15 seconds | 4–15 seconds | 4–30 seconds |
| Output resolution | 480P / 720P / 1080P / 4K | 480P / 720P | 480P / 720P / 1080P |
| Input and references | Text + image / video / audio references | Text + image / video / audio references | Text + image / video / audio references |
| Reference capacity | 9 images · 3 videos · 3 audio files | 9 images · 3 videos · 3 audio files | 30 images · 10 videos · 10 audio files |
| Aspect ratios | 21:9 · 16:9 · 4:3 · 1:1 · 3:4 · 9:16 | 21:9 · 16:9 · 4:3 · 1:1 · 3:4 · 9:16 | 21:9 · 16:9 · 4:3 · 1:1 · 3:4 · 9:16 |
| Native synchronized audio | Supported | Supported | Supported |
Start Creating With Seedance 2.0
Set up the brief now, then continue in the shared Studio workspace.